Surveillance system and method for predicting patient falls using motion feature patterns

Abstract

A method and system for detecting a fall risk condition, the system comprising a surveillance camera configured to generate a plurality of frames showing an area in which a patient at risk of falling is being monitored, and a computer system comprising memory and logic circuitry configured to store motion feature patterns that are extracted from video recordings, the motion feature patterns are representative of motion associated with real alarm cases and false-alarm cases of fall events, receive a fall alert from a classifier, determine motion features of one or more frames from the plurality of frames that correspond to the fall alert; compare the motion features of the one or more frames with the motion feature patterns, and determine whether to confirm the fall alert based on the comparison.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]The present application is a continuation of U.S. patent application Ser. No. 15 / 824,552, entitled “SURVEILLANCE SYSTEM AND METHOD FOR PREDICTING PATIENT FALLS USING MOTION FEATURE PATTERNS,” filed on Nov. 28, 2017, which claims the priority of U.S. Provisional Application No. 62 / 530,380, entitled “System and Method for Predicting Patient Falls,” filed on Jul. 10, 2017.[0002]The present application is related to the following patents and applications, which are assigned to the assignee of the present invention:[0003]U.S. Pat. No. 7,477,285, filed Dec. 12, 2003, entitled “Non-intrusive Data Transmission Network for Use in an Enterprise Facility and Method for Implementing,”[0004]U.S. Pat. No. 7,987,069, filed Nov. 11, 2008, entitled “Monitoring Patient Support Exiting and Initiating Response,”[0005]U.S. Pat. No. 8,471,899, filed Oct. 27, 2009, entitled “System and Method for Documenting Patient Procedures,”[0006]U.S. Pat. No. 8,675,059, fi...

AI Technical Summary

Problems solved by technology

Healthcare facilities invest a huge amount of their resources in falls management programs and assessing the risk of falls in a particular patient class, location, and care state, along with the risk factors associated with significant injuries.

Round the clock patient monitoring by a staff nurse is expensive, therefore, healthcare facilities have investigated alternatives in order to reduce the monitoring staff, while increasing patient safety.

Such automated systems may be susceptible to false-alarms, which can burden a staff of healthcare professionals with unnecessary interventions.

Images